docs-guard
Reviews technical documentation before publication. Ensures the quality and accuracy of manuals, tutorials, and release notes.
What it does
Checks if AI-generated documentation is correct and matches the actual code. It ensures everything written about the code, like function names and examples, is accurate.
When to use it
- ✓After the AI writes a README.
- ✓When reviewing API documentation.
- ✓Before publishing tutorials or guides.
Example of what to ask your AI
“Review this documentation to ensure all code examples work and function names are correct.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
It compares what's written in the documentation against the actual code. If there are any differences or anything that can't be verified, it points out the error.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add sickn33/agentic-awesome-skills --skill docs-guardOr download just the file:
curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/docs-guard/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Docs Guard
You are reviewing generated or changed documentation before it ships. Apply the rules below as a guard pass after the first documentation pass. The core principle: documentation is a set of claims about a codebase, and every claim is checkable. Your job is to check them.
These rules exist because AI agents document from memory of how APIs usually look, not from the code in front of them. Published research: half of AI answers to programming questions contain incorrect information, and models produce valid invocations for infrequent APIs barely a third of the time — yet the prose sounds authoritative either way. Readers cannot tell verified docs from hallucinated docs. You can, because you have the source.
When to Use
Use this skill when reviewing generated or changed documentation before it ships. Activate it reactively after an agent writes or updates READMEs, API references, docstrings, PHPDoc/JSDoc, changelogs, tutorials, or doc sites.
How to use this skill
Guard-pass mode (recommended): after documentation or docstrings have been generated or edited, verify every claim against the source and run the self-check before delivery.
Live mode (explicit): when the user invokes this skill before writing docs, verify before you write — read the actual implementation, then document what it does. Run the self-check before delivery.
Review mode (the user asks you to review, audit, or fact-check docs): walk references/review-checklist.md against the target docs and produce a findings report with file:line evidence. Do not rewrite in review mode unless asked.
Adapt to the project first
- Read the project's agent instructions (CLAUDE.md, AGENTS.md) and any docs style guide. Project conventions win on conflict.
- Identify the docs surfaces that must move together: README, reference docs, docstrings, changelog, examples, config samples. A change to one usually owes a change to others (Rule 6).
- Note the documented version policy: which versions does the project support, and where are features version-tagged?
The Rules
Accuracy — must fix
Every referenced symbol must exist. Every function, method, class, hook, CLI command, flag, endpoint, config key, env var, and file path mentioned in the docs gets verified against the actual source, CLI help output, route table, or schema — by reading it, not recalling it. The verification procedure is in references/verification.md. An unverifiable reference does not ship.
Every code sample must work. Imports resolve, APIs exist with the documented signatures (names, argument order, defaults, return shape), and the sample runs outside the author's machine — no hardcoded local paths, no real credentials, no implicit prior state. Sample rules: references/code-samples.md.
Document the code's actual behavior, not its intended behavior. Read the implementation before describing it. Where code and comments/specs disagree, the code is the truth — and flag the disagreement to the user instead of silently picking a side.
No unverifiable claims. Performance numbers, compatibility matrices, scale limits, and "production-ready" assertions require a source in the repository (benchmark script, CI matrix, changelog entry) or they come out. "Fast" is marketing; "O(n log n), benchmarked in bench/sort.md" is documentation.
Versioning and drift
Versions are explicit. Features, flags, and behaviors state the version that introduced them when the project tracks versions. Prerequisites are pinned or ranged, never "latest". Deprecated items say so, with the replacement.
A code change owes a docs change. When editing code whose behavior is documented — rename, signature change, new default, removed flag — update every doc surface that mentions it in the same change. Grep the docs for the old symbol before finishing.
Substance — should fix
- No filler, no slop. Delete: docstrings that paraphrase the signature ("Gets the user by ID" above
get_user_by_id), sections that restate their heading, marketing adjectives in technical prose ("powerful", "seamless", "blazingly fast"), and intro padding ("In this section, we will explore…"). A docstring earns its place by adding contracts the signature cannot express: units, ranges, error conditions, side effects, threading/ordering guarantees.
…
FAQ
Why might AI make mistakes in documentation?
AI might rely on how things usually are, rather than the exact code being documented, leading to errors.
What are 'claims' in documentation?
These are the pieces of information the documentation presents about the code, such as what a function does, what parameters it accepts, or how to use it.
What is 'Guard-pass mode'?
This is the recommended mode where the AI reviews the documentation after it has been written, to ensure everything is correct before it's published.
Details
Original description by the author
Review generated or changed documentation before it ships, including READMEs, API references, docstrings, changelogs, tutorials, and documentation sites.
Popularity
- GitHub stars
- 48k
- Ranking position
- #2866
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
00-andruia-consultant
Helps your agent start or improve AI projects. It analyzes code, suggests tools, and creates action plans in Spanish.
sickn33/agentic-awesome-skills
007
Lets your agent perform security audits and threat modeling. It's useful for protecting projects against attacks and vulnerabilities.
sickn33/agentic-awesome-skills
10-andruia-skill-smith
Helps your agent create or improve AI tools. It defines how tools work, writes documentation, and validates the structure.
sickn33/agentic-awesome-skills
20-andruia-niche-intelligence
Lets your agent create a summary about a specific industry. It's useful for understanding the context, rules, usage patterns, and risks of a project, using reliable sources.
sickn33/agentic-awesome-skills
Similar skills
intent-driven-development
Helps your agent turn ideas into clear, testable plans. Defines criteria to ensure changes are made correctly and safely.
affaan-m/ECC
product-capability
Guides your agent in turning product ideas into clear plans. It defines what needs to be done, the limits, and decisions before development.
affaan-m/ECC
article-writing
Writes long-form content like articles, guides, and blog posts with a unique style. It's useful when you need well-written texts with a consistent voice and credibility.
affaan-m/ECC